Merge pull request #93 from DrewThomasson/v2.0_update_readme

V2.0 update readme improved and added assets folder

legacy/v1.0/Dockerfile

@@ -0,0 +1,93 @@
+# Use an official NVIDIA CUDA image with cudnn8 and Ubuntu 20.04 as the base
+FROM nvidia/cuda:11.8.0-cudnn8-runtime-ubuntu20.04
+
+# Set non-interactive installation to avoid timezone and other prompts
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Install necessary packages including Miniconda
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    wget \
+    git \
+    espeak \
+    espeak-ng \
+    ffmpeg \
+    tk \
+    mecab \
+    libmecab-dev \
+    mecab-ipadic-utf8 \
+    build-essential \
+    calibre \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN ebook-convert --version
+
+# Install Miniconda
+RUN wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O ~/miniconda.sh && \
+    bash ~/miniconda.sh -b -p /opt/conda && \
+    rm ~/miniconda.sh
+
+
+
+# Set PATH to include conda
+ENV PATH=/opt/conda/bin:$PATH
+
+# Create a conda environment with Python 3.10
+RUN conda create -n ebookenv python=3.10 -y
+
+# Activate the conda environment
+SHELL ["conda", "run", "-n", "ebookenv", "/bin/bash", "-c"]
+
+# Install Python dependencies using conda and pip
+RUN conda install -n ebookenv -c conda-forge \
+    pydub \
+    nltk \
+    mecab-python3 \
+    && pip install --no-cache-dir \
+    bs4 \
+    beautifulsoup4 \
+    ebooklib \
+    tqdm \
+    tts==0.21.3 \
+    unidic \
+    gradio
+
+# Download unidic
+RUN python -m unidic download
+
+# Set the working directory in the container
+WORKDIR /ebook2audiobookXTTS
+
+# Clone the ebook2audiobookXTTS repository
+RUN git clone https://github.com/DrewThomasson/ebook2audiobookXTTS.git .
+
+# Copy test audio file
+COPY default_voice.wav /ebook2audiobookXTTS/
+
+# Run a test to set up XTTS
+RUN echo "import torch" > /tmp/script1.py && \
+    echo "from TTS.api import TTS" >> /tmp/script1.py && \
+    echo "device = 'cuda' if torch.cuda.is_available() else 'cpu'" >> /tmp/script1.py && \
+    echo "print(TTS().list_models())" >> /tmp/script1.py && \
+    echo "tts = TTS('tts_models/multilingual/multi-dataset/xtts_v2').to(device)" >> /tmp/script1.py && \
+    echo "wav = tts.tts(text='Hello world!', speaker_wav='default_voice.wav', language='en')" >> /tmp/script1.py && \
+    echo "tts.tts_to_file(text='Hello world!', speaker_wav='default_voice.wav', language='en', file_path='output.wav')" >> /tmp/script1.py && \
+    yes | python /tmp/script1.py
+
+# Remove the test audio file
+RUN rm -f /ebook2audiobookXTTS/output.wav
+
+# Verify that the script exists and has the correct permissions
+RUN ls -la /ebook2audiobookXTTS/
+
+# Check if the script exists and log its presence
+RUN if [ -f /ebook2audiobookXTTS/custom_model_ebook2audiobookXTTS_with_link_gradio.py ]; then echo "Script found."; else echo "Script not found."; exit 1; fi
+
+# Modify the Python script to set share=True
+RUN sed -i 's/demo.launch(share=False)/demo.launch(share=True)/' /ebook2audiobookXTTS/custom_model_ebook2audiobookXTTS_with_link_gradio.py
+
+# Download the punkt package for nltk
+RUN python -m nltk.downloader punkt
+
+# Set the command to run your GUI application using the conda environment
+CMD ["conda", "run", "--no-capture-output", "-n", "ebookenv", "python", "/ebook2audiobookXTTS/custom_model_ebook2audiobookXTTS_with_link_gradio.py"]
+

legacy/v1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Drew Thomasson
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

legacy/v1.0/Notebooks/Kaggel Archive Code/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 Drew Thomasson
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

legacy/v1.0/Notebooks/Kaggel Archive Code/README.md

@@ -0,0 +1,118 @@
+# this is a sample for running on kaggle and it may not be updated frequently
+
+# ebook2audiobook kaggle eddition
+Generates an audiobook with chapters and ebook metadata using Calibre and Xtts from Coqui tts, and with optional voice cloning, and supports multiple languages
+
+# import this notebook to kaggle
+https://github.com/Rihcus/ebook2audiobookXTTS/blob/main/kaggle-ebook2audiobook-demo.ipynb
+
+## Features
+
+- Converts eBooks to text format using Calibre's `ebook-convert` tool.
+- Splits the eBook into chapters for structured audio conversion.
+- Uses XTTS from Coqui TTS for high-quality text-to-speech conversion.
+- Optional voice cloning feature using a provided voice file.
+- Supports different languages for text-to-speech conversion, with English as the default.
+- Confirmed to run on only 4 gb ram
+
+## Requirements
+
+- Python 3.x
+- `coqui-tts` Python package
+- Calibre (for eBook conversion)
+- FFmpeg (for audiobook file creation)
+- Optional: Custom voice file for voice cloning
+
+### Installation Instructions for Dependencies
+
+Install Python 3.x from [Python.org](https://www.python.org/downloads/).
+
+Install Calibre:
+- Ubuntu: `sudo apt-get install -y calibre`
+- macOS: `brew install calibre`
+- Windows(Powershell in Administrator mode): `choco install calibre` 
+
+Install FFmpeg:
+- Ubuntu: `sudo apt-get install -y ffmpeg`
+- macOS: `brew install ffmpeg`
+- Windows(Powershell in Administrator mode): `choco install ffmpeg` 
+
+Install Mecab for (Non Latin-based Languages tts support)(Optional):
+- Ubuntu: `sudo apt-get install -y mecab libmecab-dev mecab-ipadic-utf8`
+- macOS: `brew install mecab`, `brew install mecab-ipadic`
+- Windows(Powershell in Administrator mode no support for mecab-ipadic easy install so no Japanese for windows :/): `choco install mecab ` 
+
+Install Python packages:
+```bash
+pip install tts pydub nltk beautifulsoup4 ebooklib tqdm
+```
+(For non Latin-based Languages tts support)(Optional)  
+`python -m unidic download`
+```bash
+pip install mecab mecab-python3 unidic
+```
+
+### Supported Languages
+
+The script supports the following languages for text-to-speech conversion:
+
+English (en),
+Spanish (es),
+French (fr),
+German (de),
+Italian (it),
+Portuguese (pt),
+Polish (pl),
+Turkish (tr),
+Russian (ru),
+Dutch (nl),
+Czech (cs),
+Arabic (ar),
+Chinese (zh-cn),
+Japanese (ja),
+Hungarian (hu),
+Korean (ko)
+
+Specify the language code when running the script to use these languages.
+
+### Usage
+
+Navigate to the script's directory in the terminal and execute one of the following commands:
+If you have any trouble getting it to run in Windows then it should run fine in WSL2
+
+Basic Usage: ALL PARAMETERS ARE MANDATORY WHEN CALLED THE SCRIPT
+
+```bash
+python ebook2audiobook.py <path_to_ebook_file> [path_to_voice_file] [language_code]
+```
+Replace <path_to_ebook_file> with the path to your eBook file.
+include <path_to_voice_file> for voice cloning.
+include <language_code> to specify the language
+
+
+## Demo
+
+
+
+https://github.com/DrewThomasson/ebook2audiobookXTTS/assets/126999465/bccd7240-f967-4d27-a87d-445034db7d21
+
+
+
+### Supported ebook File Types: 
+.epub, .pdf, .mobi, .txt, .html, .rtf, .chm, .lit, .pdb, .fb2, .odt, .cbr, .cbz, .prc, .lrf, .pml, .snb, .cbc, .rb, and .tcr,
+(Best results are from using epub or mobi for auto chapter detection)
+
+### outputs as a m4b with all book metadata and chapters, example output file in an audiobook player app
+![Example_of_output_in_audiobook_program](https://github.com/DrewThomasson/VoxNovel/blob/dc5197dff97252fa44c391dc0596902d71278a88/readme_files/example_in_app.jpeg)
+
+A special thanks to the creaters of:
+
+
+-Coqui TTS
+
+-https://github.com/coqui-ai/TTS
+
+
+-Calibre
+
+-https://calibre-ebook.com

legacy/v1.0/Notebooks/Kaggel Archive Code/Worker_2T4.sh

@@ -0,0 +1,59 @@
+#!/bin/bash
+
+workers=$1
+
+# Clean up operator directory
+rm -rf "./Operator"
+rm -rf "./Chapter_wav_files"
+mkdir "./Operator"
+mkdir "./Chapter_wav_files"
+
+
+# Make appropriate temp directories
+for i in $(seq 1 $workers); do
+    mkdir "./Operator/$i"
+    mkdir "./Operator/$i/temp"
+    mkdir "./Operator/$i/temp_ebook"
+done
+
+echo "Created $workers directories"
+
+#Divide the chapters
+share=1
+for FILE in ./Working_files/temp_ebook/*; do
+    cp $FILE "./Operator/$share/temp_ebook/"
+    if [ $share -lt $workers ];
+    then
+        share=$((share+1))
+    else
+        share=1
+    fi
+done
+
+echo "Split chapters into operator"
+
+#Run audio generation
+#for i in $(seq 1 $workers); do
+#    echo "Starting Worker $i"
+#    python p2a_worker.py $i &
+#done
+
+gpu=1
+for i in $(seq 1 $workers); do
+    if [ $gpu -lt 2 ];
+    then
+        echo "Starting Worker $i on GPU 1"
+        python p2a_worker_gpu1.py $i & #Run audio generation GPU 1 T4
+        gpu=2 # switch to gpu 2 on next loop
+    else
+        echo "Starting Worker $i on GPU 2"
+        python p2a_worker_gpu2.py $i & #Run audio generation GPU 2 T4
+        gpu=1 # switch to gpu 1 on next loop
+    fi
+done
+
+
+
+echo "All workers started waiting for completion...."
+wait
+echo "Done!"

legacy/v1.0/Notebooks/Kaggel Archive Code/kaggle-ebook2audiobook-demo.ipynb

@@ -0,0 +1 @@
+{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.13","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[],"dockerImageVersionId":30733,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"Install depdenencies","metadata":{}},{"cell_type":"code","source":"#!DEBIAN_FRONTEND=noninteractive\n!sudo apt-get update # && sudo apt-get -y upgrade\n!sudo apt-get -y install libegl1 \n!sudo apt-get -y install libopengl0\n!sudo apt-get -y install libxcb-cursor0\n!sudo -v && wget -nv -O- https://download.calibre-ebook.com/linux-installer.sh | sudo sh /dev/stdin\n!sudo apt-get install -y ffmpeg\n!pip install tts pydub nltk beautifulsoup4 ebooklib tqdm\n!pip install numpy==1.26.4","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2024-06-17T21:17:43.474429Z","iopub.execute_input":"2024-06-17T21:17:43.474679Z","iopub.status.idle":"2024-06-17T21:20:20.992799Z","shell.execute_reply.started":"2024-06-17T21:17:43.474655Z","shell.execute_reply":"2024-06-17T21:20:20.991791Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Download modified ebook2audiobookXTTS\nhttps://github.com/Rihcus/ebook2audiobookXTTS\n\nOrigional unmodified version\nhttps://github.com/DrewThomasson/ebook2audiobookXTTS","metadata":{}},{"cell_type":"code","source":"!git clone https://github.com/Rihcus/ebook2audiobookXTTS","metadata":{"execution":{"iopub.status.busy":"2024-03-25T23:22:24.156772Z","iopub.execute_input":"2024-03-25T23:22:24.157618Z","iopub.status.idle":"2024-03-25T23:22:26.202486Z","shell.execute_reply.started":"2024-03-25T23:22:24.157577Z","shell.execute_reply":"2024-03-25T23:22:26.201179Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"(optional) Uploading your own epub book.\n\nBy default this notebook will use a sample epub book for testing/demo. \n\nIf you want to use your own book you will need to create a private kaggle data set, upload your epub to it, attach it to this notebook, and uncomment the two lines of code bellow, and update the data set path","metadata":{}},{"cell_type":"code","source":"# !cp -r /kaggle/input/<name of your attached dataset>/*.epub /kaggle/working/ebook2audiobookXTTS #copy your custom book\n# !rm /kaggle/working/ebook2audiobookXTTS/demo_mini_story_chapters_Drew.epub #remove default sample book","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"This to install xtts_v2 models","metadata":{}},{"cell_type":"code","source":"import os\nos.environ[\"COQUI_TOS_AGREED\"] = \"1\"\n\n!cd /kaggle/working/ebook2audiobookXTTS && tts --model_name tts_models/multilingual/multi-dataset/xtts_v2 --text \"test\" --speaker_wav ./4.wav --language_idx en --use_cuda true","metadata":{"execution":{"iopub.status.busy":"2024-03-25T23:23:15.626677Z","iopub.execute_input":"2024-03-25T23:23:15.627585Z","iopub.status.idle":"2024-03-25T23:27:40.712856Z","shell.execute_reply.started":"2024-03-25T23:23:15.627548Z","shell.execute_reply":"2024-03-25T23:27:40.711852Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"This is a modified version of ebook2audiobookXTTS. \n\n- p1.py only runs the first part ebook2audiobookXTTS and generates chapter txts (I commented out other parts)\n    - https://github.com/Rihcus/ebook2audiobookXTTS/blob/main/p1.py\n- Worker_2T4.sh as a basic attempt at multigpu support. The 4 argument processes of ebook2audiobook will be run in parallel\n    - Worker_2T4 will try to divide the chapter in even groups based on number of workers (ex 4 group 4 workers)\n    - It will try to divy up the work between kaggles two T4 GPUS\n    - I'm not sure how much of a difference it makes since kaggles cpu limitations\n    \nhttps://github.com/Rihcus/ebook2audiobookXTTS/blob/main/Worker_2T4.sh\n\nhttps://github.com/Rihcus/ebook2audiobookXTTS/blob/main/p2a_worker_gpu1.py\n\nhttps://github.com/Rihcus/ebook2audiobookXTTS/blob/main/p2a_worker_gpu2.py","metadata":{}},{"cell_type":"code","source":"!cd /kaggle/working/ebook2audiobookXTTS && python p1.py \"$(ls ./*.epub)\" \"4.wav\" \"en\"\n!cd /kaggle/working/ebook2audiobookXTTS && bash Worker_2T4.sh 4","metadata":{},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"p3.py runs the final ffmpeg command. ffmpeg has been a bit buggy\nhttps://github.com/Rihcus/ebook2audiobookXTTS/blob/main/p3.py","metadata":{}},{"cell_type":"code","source":"!cd /kaggle/working/ebook2audiobookXTTS && python p3.py \"$(ls ./*.epub)\" \"4.wav\" \"en\"","metadata":{},"execution_count":null,"outputs":[]}]}